achao2013
achao2013
@piiswrong i have copied the code from the deep3d.ipynb to deep3d.py, then i run the deep3d.py and encounter this error
i remember it's caused by torchsparse, its version should be 1.4 and cuda version should be 10.2, and you can look up the versions of other dependent libraries in my...
you can pip install it separately.
sorry , the pytorch3d may be hard to install，you can reference to the official website of pytorch3d
@qianqianwang68
> x_i and x_j share the same density (not blending weight), and that's because they correspond to the same canonical 3D point. In our work, all local 3D locations that...
Can you help me to solve my confusion? 1.If a point x_i moved, the sample points in the ray of frame i might not be on the same straight line...
Thank you for your detailed and patient explanation. Sorry to reply you later. I have understand the previous problems. For the last problem mentioned above, i firstly highlight the related...
@qianqianwang68
ok, thanks. So I think the sentence "the canonical coordinate u is time-independent" is not exactly right, because if u is not in a specific time t, it can be...